Method for constructing marker microsatellite locus stability prediction model

By constructing a prediction model for labeling microsatellite sites, using machine learning algorithms to directly predict the overall state of MSI from second-generation sequencing data, the problem of low reliability of normal sample pairing and sequencing in the existing technology is solved, and MSI detection is realized Fast, accurate and efficient.

CN118942537AActive Publication Date: 2024-11-12HANGZHOU LIANKANG MEDICAL LAB CO LTD
View PDF 10 Cites 0 Cited by

Patent Information

Application Number
CN202410929917.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-09-21
Publication Date
2024-11-12
Estimated Expiration
2043-09-21

AI Technical Summary

Technical Problem

The existing MSI detection technology requires normal sample pairing, which is complex and inconvenient, and the single-bit sequencing reliability of second-generation sequencing microsatellite site data is low, resulting in low detection accuracy and efficiency.

Method used

Provide a method without normal sample pairing, construct a prediction model through labeled microsatellite sites and machine learning algorithms, and directly predict the test to be measured using labeled microsatellite sites data input module, MSI overall state storage module and MSI overall state determination module. The overall state of the MSI of the sample, including the stability data input, storage and prediction modules that label microsatellite sites, uses random forest or logistic regression algorithm to build a stability prediction model.

Benefits of technology

It realizes fast, accurate and repeatable prediction of the overall MSI status, reduces the limitations of detection, and does not require normal sample pairing, and is suitable for different NGS detection platforms and cancer species.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942537A_ABST
    Figure CN118942537A_ABST
Patent Text Reader

Abstract

The invention discloses a method for constructing a marker microsatellite locus stability prediction model, and belongs to the technical field of MSI detection. According to the method, the regression model is established through the known microsatellite loci, and the stability of the 22 marked microsatellite loci is predicted. The stability data of the marked microsatellite sites are obtained by using the method disclosed by the invention, and a machine learning model can be further established to predict the overall state of the MSI. By utilizing the method, the MSI overall state can be predicted without normal sample pairing in different NGS detection platforms and different cancer species by analyzing the next-generation sequencing data, the method is stable and rapid, the result is accurate, the repeatability is high, and the detection limitation is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] Related patents

[0002] This application is a divisional application of the Chinese invention patent application with application number 2023112243588, application date September 21, 2023, and invention name “Microsatellite loci, systems and kits for predicting MSI status”. Technical Field

[0003] The invention belongs to the technical field of MSI detection, and in particular, relates to a method for constructing a prediction model for the stability of a marker microsatellite site. Background Art

[0004] Microsatellite instability (MSI) refers to the phenomenon of changes in the length of microsatellite (MS) sequences caused by insertion or deletion mutations during DNA replication, which is often caused by mismatch repair (MMR) defects. MS sequences are short and repetitive DNA sequences, generally composed of 1 to 6 nucleotides, arranged in tandem repeats, and common types are double bases CA / GA / GT or single bases A / T. MS sequences can be located in important non-coding regions of genes or in coding regions of genes. Polymorphisms are distributed throughout the genome and vary greatly from individual to individual. Cells can repair regions where mismatches occur during genome replication through mismatch repair elements. In some cases, mismatch repair elements lose their original functions, such as mutations in MLH1, MSH2, MSH6, etc., which result in cells being unable to repair mismatches and causing MSI phenotypes in cells. This phenotype is reflected in changes in the number of microsatellite unit repeats, which may become longer or shorter.

[0005] Microsatellite instability is a relatively common phenomenon in tumors. The state of microsatellite instability indicates the cause and development of the tumor, and can also play an important role in auxiliary diagnosis and medication guidance in different types of cancer. Generally, the state of microsatellite instability can be divided into microsatellite high instability (MSI-H), microsatellite low instability (MSI-L) and microsatellite stable (MSS). In colorectal cancer, endometrial cancer, gastric cancer and other cancers, patients with MSI-H status have significant differences in survival, medication preference, and palliative treatment prognosis compared with the other two. MSI testing can help doctors fully understand the type of cancer and propose correct diagnosis and treatment plans.

[0006] Another important role of MSI testing is to assist in screening for Lynch Syndrome, a hereditary syndrome in which germline mutations in mismatch repair genes occur, characterized by colorectal cancer, endometrial cancer, and gastric cancer, which occur at a younger age and have related cancers in the family. MSI status has a certain correlation with Lynch syndrome, and the vast majority of patients with stable microsatellites do not have Lynch syndrome. Traditionally, if a patient has the above symptoms, doctors usually consider detailed testing. If immunohistochemistry is used, two experienced pathologists are required to conduct the test together, and the accuracy rate is low. If MSI testing is used, it is more convenient and has a higher accuracy rate. When a patient is judged to be MSI-H, a comprehensive genetic diagnosis can be continued to determine whether it is Lynch syndrome.

[0007] Due to the sequence characteristics of MSI sites, the sequencing reliability of a single site is low. MSI detection based on second-generation sequencing usually detects hundreds or thousands of MSI sites. Multi-site cloning detection and genome sequencing methods can be used to detect microsatellite status. The multi-site cloning method is common in current MSI detection. It determines whether the length of 5 to dozens of microsatellite regions that are highly correlated with the MSI status has changed, and determines whether the site is unstable according to the degree of change. The higher the proportion of unstable sites, the more likely the cell is to be in an MSI state. This method is inexpensive and has a short experimental process. However, many current detection tools that predict MSI status through NGS methods require normal sample pairing, such as mSINGS, MANTIS, etc. Summary of the invention

[0008] The main purpose of the present invention is to provide a method for predicting the overall status of MSI without normal sample pairing for liquid phase capture second-generation sequencing microsatellite locus data. The method is easy to calculate, stable and fast, with accurate results and high repeatability, which reduces the limitations of detection.

[0009] To achieve the above purpose, the technical solution provided by the present invention is as follows:

[0010] The first aspect of the present invention provides a marker microsatellite locus for determining the overall MSI status of a sample to be tested, the marker microsatellite locus comprising:

[0011]

[0012]

[0013] Microsatellite (MS) refers to short tandem repeat (STR) in the human genome, or repeated base sequence, including single nucleotide repeats, double nucleotide repeats, and even more nucleotide repeats. Microsatellite instability (MSI) refers to the change of any length of microsatellite in tumor tissue due to the insertion or deletion of repeating units relative to normal tissue. In the present invention, the overall MSI status refers to the status of all microsatellites in the sample to be tested; the microsatellite site refers to a specific microsatellite site, and the marker microsatellite site refers to a microsatellite used to determine the overall MSI status of the sample to be tested.

[0014] In the present invention, microsatellites containing other mononucleotide repeat sequences and / or dinucleotide repeat sequences may also be selected or used as marker microsatellite loci.

[0015] In the present invention, the number of repeats is the standard value (γ) of the length of the marker microsatellite locus, that is, the number of repeats (standard number of repeats) in the above table.

[0016] In the present invention, since the length of a microsatellite is changed by the insertion or deletion of a repeating unit, the length of the microsatellite is the specific number of repetitions of the repeating unit, that is, the length is the number of repetitions. For example, even if the number of bases in the repeating unit is 2, it is repeated 10 times and the base length is 20, the length of the microsatellite locus is still considered to be 10.

[0017] For microsatellite loci, each repeating unit has three states: deletion, unchanged, and insertion, that is, the number of each repeating unit can be 0, 1, or 2. Based on this, for each microsatellite locus, the length range is [0, 2γ].

[0018] The second aspect of the present invention provides the use of the detection reagent for marking microsatellite loci according to the first aspect of the present invention in the preparation of a kit for determining the overall MSI status of a sample to be tested.

[0019] A third aspect of the present invention provides a system for determining the overall MSI status of a sample to be tested, comprising the following modules:

[0020] A marker microsatellite locus data input module, used to receive stability data of the marker microsatellite locus of the first aspect of the present invention of the sample to be tested, wherein the stability includes stable and unstable;

[0021] An MSI overall status storage module is used to store the stability data of the marker microsatellite loci and the MSI overall status data of the second population sample, wherein the MSI overall status includes MSI-H, MSI-L and MSS;

[0022] an MSI overall status determination module, connected to the data input module and the MSI overall status storage module respectively, for constructing a prediction model using the stability data of the marker microsatellite loci of the second population sample, and determining the MSI overall status of the sample to be tested based on the stability data of the marker microsatellite loci of the sample to be tested obtained from the marker microsatellite loci stability prediction module.

[0023] In some embodiments of the present invention, the stability data of the marker microsatellite site refers to whether the length of the marker microsatellite site changes. If a marker microsatellite site changes significantly, that is, the length of the marker microsatellite site changes significantly due to the insertion or deletion of a repeating unit, then the marker microsatellite site is unstable; conversely, if a marker microsatellite site does not change, that is, there is no change in the length of the marker microsatellite site due to the insertion or deletion of a repeating unit, or even if there is an insertion or deletion of a repeating unit, the length change is not significant, then the marker microsatellite site is stable.

[0024] In the present invention, the meanings of MSI-H, MSI-L and MSS are as follows:

[0025] (1) MSS: Microsatellite Stability, that is, all microsatellite loci are in a stable state.

[0026] (2) MSI-L: Low-frequency MSI, low-frequency microsatellite instability, that is, microsatellite loci that are less than the preset threshold are in an unstable state.

[0027] (3) MSI-H: High-frequency MSI, high-frequency microsatellite instability, that is, microsatellite loci that are not less than the preset threshold are in an unstable state.

[0028] In some embodiments of the present invention, the preset threshold may be an absolute value of the quantity or a ratio, such as 30%.

[0029] In some embodiments of the present invention, in the MSI overall status determination module, constructing a prediction model using the stability data of the marker microsatellite loci of the population sample comprises the following steps:

[0030] S21, randomly dividing the stability data of the marker microsatellite loci of the second population samples into two groups, one group is a second training set, and the other group is a second test set, each group includes the stability data of the marker microsatellite loci of the MSI-H samples, the MSI-L samples and the MSS samples;

[0031] S22, using the second training set data, constructing an MSI overall status prediction model based on a machine learning algorithm;

[0032] S23, in the second test set, verifying the obtained MSI overall status prediction model.

[0033] In some embodiments of the invention, the machine learning algorithm is selected from any one of the following algorithms:

[0034] Random forest algorithm, neural network algorithm, support vector machine algorithm, Bayesian classification algorithm, gradient boosting algorithm, K nearest neighbor algorithm and decision tree algorithm.

[0035] In some preferred embodiments of the present invention, the MSI overall status prediction model is obtained by training using a random forest model.

[0036] In some embodiments of the present invention, the stability data of the marker microsatellite loci obtained in the marker microsatellite loci data input module is obtained based on a PCR method.

[0037] Furthermore, the system further comprises:

[0038] A sequencing data input module, used to input the captured sequencing data of the target region containing the marker microsatellite site in the sample to be tested, and obtain the number of peaks, kurtosis, skewness, standard deviation and standard deviation of the length of the marker microsatellite site;

[0039] A microsatellite locus storage module is used to store the peak number, kurtosis, skewness, standard deviation and standard shift of the known microsatellite locus lengths of the first population sample and stability data;

[0040] The marker microsatellite site stability prediction module is connected to the sequencing data input module, the marker microsatellite site storage module and the marker microsatellite site data input module respectively, and is used to construct a marker microsatellite site stability prediction model using the peak number, kurtosis, skewness, standard deviation and standard deviation of the known microsatellite site length of the first population sample and the stability data, and predict the stability of the marker microsatellite site based on the peak number, kurtosis, skewness, standard deviation and standard deviation of the marker microsatellite site length obtained from the sequencing data input module, and output the stability data of the marker microsatellite site to the marker microsatellite site data input module.

[0041] In some embodiments of the present invention, the known microsatellite loci include:

[0042]

[0043]

[0044] In some embodiments of the present invention, in the marker microsatellite site stability prediction module, the use of the peak number, kurtosis, skewness, standard deviation and standard deviation of the known microsatellite site length and stability data to construct a marker microsatellite site stability prediction model comprises the following steps:

[0045] S11, randomly divide the peak number, kurtosis, skewness, standard deviation, standard shift and stability data of the known microsatellite loci length of the first population samples into two groups, one group is the first training set, and the other group is the first test set;

[0046] S12, using the first training set data, constructing a marker microsatellite locus stability prediction model based on a regression algorithm;

[0047] S13, in the first test set, verifying the obtained marker microsatellite site stability prediction model.

[0048] In some embodiments of the present invention, the regression algorithm is selected from any one of the following algorithms: logistic regression algorithm, linear regression algorithm.

[0049] In some embodiments of the present invention, for any of the marker microsatellite loci, the number of peaks of the marker microsatellite locus length is first counted according to the peak finding algorithm, and then the skewness Skew, kurtosis Kurt, standard deviation S and standard deviation P of the marker microsatellite locus length are calculated respectively:

[0050] Skewness measures the asymmetry of the probability distribution of a random variable. It is a measure of the degree of asymmetry relative to the mean value. By measuring the skewness coefficient, the degree of asymmetry and direction of the distribution of the length of the marker microsatellite locus can be determined. The skewness is measured relative to the normal distribution. The skewness of the normal distribution is 0, that is, if the distribution of the length of the marker microsatellite locus is symmetrical, the skewness is 0. If the skewness is greater than 0, the distribution is right-skewed, that is, the distribution has a long tail on the right; if the skewness is less than 0, the distribution is left-skewed, that is, the distribution has a long tail on the left; at the same time, the larger the absolute value of the skewness, the more serious the degree of deviation of the distribution.

[0051] The skewness calculation formula is:

[0052]

[0053] Among them, x iis the number of reads when the length of the marker microsatellite site is i, i = [1, n]; is the mean of the number of reads of different lengths of the marker microsatellite site; n is the number of length types of the marker microsatellite site, that is, how many different lengths it has, n=2γ; γ is the standard value of the length of the marker microsatellite site.

[0054] Kurtosis is a statistic that studies whether the data distribution is steep or smooth. By measuring the kurtosis coefficient, it can be determined whether the length of the marker microsatellite site is steeper or flatter than the normal distribution. If the kurtosis = 3, the kurtosis of the marker microsatellite site length distribution follows the normal distribution; if the kurtosis > 3, the kurtosis of the marker microsatellite site length distribution is steep (high and pointed); if the kurtosis < 3, the kurtosis of the marker microsatellite site length distribution is flat (short and fat). The kurtosis calculation formula is:

[0055]

[0056] Among them, x i is the number of reads when the length of the marker microsatellite site is i, i = [1, n]; is the mean of the number of reads of different lengths of the marker microsatellite site; n is the number of length types of the marker microsatellite site, n=2γ, γ is the standard value of the length of the marker microsatellite site.

[0057] The standard deviation reflects the degree of dispersion of the length of the marker microsatellite locus. The larger the value, the more dispersed it is, that is, the greater the difference between different lengths of the marker microsatellite locus.

[0058] The formula for calculating standard deviation is:

[0059]

[0060] Among them, x i is the number of reads when the length of the marker microsatellite site is i, i = [1, n]; is the mean number of reads of different lengths at the marker microsatellite locus; x i ′ is the normalized value of the number of reads when the length of the microsatellite site is i, For x i ′ ; n is the length type of the marker microsatellite site, n = 2γ, γ is the standard value of the length of the marker microsatellite site.

[0061] The standard deviation refers to the level at which the length of the marker microsatellite site deviates from the standard value of the length of the marker microsatellite site.

[0062] The standard deviation calculation formula is:

[0063]

[0064] Among them, x i is the number of reads when the length of the marker microsatellite site is i, i = [1, n]; x i ' is the normalized value of the number of reads when the length of the microsatellite site is i, n is the number of length types of the marker microsatellite site; γ is the standard value of the length of the marker microsatellite site, n=2γ, γ is the standard value of the length of the marker microsatellite site.

[0065] In some embodiments of the present invention, in the sequencing data input module, the peak number, kurtosis, skewness, standard deviation and standard deviation of the marker microsatellite loci are calculated only when the depth of the capture sequencing of the target region reaches 400×. Specifically, the result file of Msisensor2 is used to calculate the number of reads of different lengths of the marker microsatellite loci.

[0066] The fourth aspect of the present invention provides a kit for determining the overall MSI status of a sample to be tested, comprising the detection reagent for marking microsatellite loci according to the first aspect of the present invention.

[0067] In the present invention, the "first population samples" and the "second population samples" are only formal areas, wherein the data of the first population samples include the number of peaks, kurtosis, skewness, standard deviation and standard deviation of the known microsatellite site lengths of each sample, as well as stability data, which are used to construct a marker microsatellite site stability prediction model based on a regression algorithm; the data of the second population samples include the stability data of the marker microsatellite sites and the MSI overall status data, which are used to construct an MSI overall status prediction model.

[0068] In the present invention, the sample to be tested is derived from humans, preferably a tumor sample, such as fresh tissue, tissue paraffin block (FFPE), etc.

[0069] Beneficial Effects of the Invention

[0070] Compared with the prior art, the present invention has the following beneficial effects:

[0071] By using the present invention, the overall MSI status can be predicted in different NGS detection platforms and different cancer types through analysis of second-generation sequencing data without the need for normal sample pairing.

[0072] The present invention is used to predict the overall status of MSI, which is stable and fast, with accurate results and high repeatability, thus reducing the limitations of detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1The length distribution diagram of a microsatellite locus in Example 3 of the present invention is shown.

[0074] Figure 2 The MSI-PCR capillary electrophoresis detection structure of a microsatellite locus in Example 4 of the present invention is shown. A: tumor sample; B: blood sample.

[0075] Figure 3 The stability performance evaluation results of the logistic regression model established in Example 4 of the present invention for predicting microsatellite loci are shown.

[0076] Figure 4 The performance evaluation results of the random forest model established in Example 5 of the present invention for predicting the overall status of MSI are shown.

[0077] Figure 5 The verification result of the external data set in Example 6 of the present invention is shown.

[0078] Figure 6 A schematic diagram of a system for determining the overall MSI status of a sample to be tested constructed in Example 7 of the present invention is shown. DETAILED DESCRIPTION

[0079] Unless otherwise indicated, implied from the context, or customary in the prior art, all parts and percentages in this application are based on weight, and the tests and characterization methods used are all synchronized with the filing date of this application. Where applicable, the contents of any patent, patent application or disclosure involved in this application are fully incorporated herein by reference, and their equivalent patent families are also introduced as references, especially the definitions of relevant terms in the art disclosed in these documents. If the definition of a specific term disclosed in the prior art is inconsistent with any definition provided in this application, the definition of the term provided in this application shall prevail.

[0080] Numerical ranges in this application are approximate values, so unless otherwise specified, they may include numerical values ​​outside the range. Numerical ranges include all numerical values ​​from the lower limit to the upper limit increased by 1 unit, provided that there is an interval of at least 2 units between any lower value and any higher value. For a range comprising a numerical value less than 1 or a range comprising a fraction greater than 1 (e.g., 1.1, 1.5, etc.), 1 unit is appropriately considered as 0.0001, 0.001, 0.01 or 0.1. For a range comprising a single digit less than 10 (e.g., 1 to 5), 1 unit is generally considered as 0.1. These are only specific examples of what is intended to be expressed, and all possible combinations of numerical values ​​between the lowest and highest values ​​listed are considered to be clearly recorded in this application.

[0081] The terms "comprising", "including", "having" and their derivatives do not exclude the presence of any other components, steps or processes, and are irrelevant to whether these other components, steps or processes are disclosed in this application. To eliminate any doubt, unless explicitly stated, all compositions using the terms "comprising", "including", or "having" in this application may include any additional additives, adjuvants or compounds. On the contrary, except for those necessary for operating performance, the term "essentially consisting of..." excludes any other components, steps or processes from the scope of any description of the term below. The term "consisting of..." does not include any components, steps or processes that are not specifically described or listed. Unless explicitly stated, the term "or" refers to the listed individual members or any combination thereof.

[0082] In order to make the technical problems, technical solutions and beneficial effects solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments.

[0083] Example

[0084] The following examples are used to demonstrate preferred embodiments of the present invention. It will be appreciated by those skilled in the art that the techniques disclosed in the following examples represent techniques discovered by the inventors that can be used to implement the present invention and therefore can be considered as preferred embodiments of the present invention. However, it will be appreciated by those skilled in the art based on this specification that many modifications may be made to the specific embodiments disclosed herein and still achieve the same or similar results without departing from the spirit or scope of the present invention.

[0085] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, and the disclosure and materials cited therein are hereby incorporated by reference.

[0086] Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many technical equivalents to the specific embodiments of the invention described herein. Such equivalents are intended to be encompassed by the claims.

[0087] The experimental methods in the following examples are conventional methods unless otherwise specified. The instruments and equipment used in the following examples are conventional laboratory instruments and equipment unless otherwise specified; the experimental materials used in the following examples are purchased from conventional biochemical reagent stores unless otherwise specified.

[0088] Example 1 Selection of microsatellite loci

[0089] 800 tissue samples from clinical tumor patients with cancers including colorectal cancer and lung cancer were collected for MSI prediction.

[0090] In the selection of microsatellite loci, this embodiment uses a large gene panel (as shown in Table 1) containing 169 gene tests related to solid tumors such as colorectal cancer, lung cancer, endometrial cancer, and gastric cancer, which is developed based on VariantBaitsTM technology. The DNA extracted from the sample is hybridized and captured using the target region probe, and then a library is constructed to obtain the corresponding sample library, which is further sequenced by the second generation sequencing to obtain the second generation sequencing raw data (raw data) in fastq format.

[0091] Table 1 List of 169 genes

[0092] AKT1 ALK APC ARAF ARID1A ATM BRAF BRCA1 BRCA2 CTNNB1 DDR2 DNMT3A EGFR ERBB2 ERBB3 FGF19 FGFR1 FGFR2 FGFR3 FGFR4 FH FLCN HFE HOXB13 IDH1 IDH2 JAK1 JAK2 KDM6A KIT KRAS MAP2K1 MDM4 MTOR NF2 NRAS NRG1 NTRK1 NTRK2 NTRK3 PDGFRA PIK3C2G PTEN RB1 RET ROS1 SDHA SDHB SMAD4 STK11 TERT TP53 TSC1 TSC2 UGT1A1 VEGFA VHL WT1 BAP1 BARD1 BRIP1 CDK12 CHEK1 CHEK2 ERCC1 FANCA FANCL MEN1 MLH1 MSH6 MUTYH NBN NF1 PALB2 PMS2 POLD1 POLE PPP2R2A RAD51C RAD51D RAD54L SDHAF2 SDHC SDHD EPCAM HLA-A HLA-B ABCB1 ABCC2 ABCC4 ATIC C8orf34 CBR3 CDA CYP19A1 CYP1B1 CYP2C8 CYP2D6 CYP3A4 DHFR DPy DYNC2H1 ERCC2 FOLR3 GGH MTHFR MTRR NQO1 RRM1 SEMA3C SLC19A1 SLC22A16 SLC22A2 SLCO1B1 TPMT TYMS UMPS XPC XRCC1 ABL1 CDH1 CDKN2A CSF1R EZH2 FBXW7 FLT3 GNAQ GNAS HNF1A JAK3 KDR NOTCH1 PBRM1 PTPN11 SMARCB1 B2M ESR1 HRAS MET PIK3CA TGFBR2 BMPR1A MSH2 RAD51B HLA-C CYP2B6 GSTP1 SOD2 ERBB4 NPM1

[0093] Example 2: Sample library construction, sequencing and sequence comparison

[0094] The quality control software Picard was used to perform quality control on the raw data obtained in Example 1, and sequencing adapters, low-quality bases, and sequencing error fragments were filtered out, and high-quality data (clean data) was obtained after filtering.

[0095] The clean data was compared and analyzed using the sequence alignment software bwa-MEM to obtain the specific genomic location information of the sequence (the reference genome was hg19); samtools and sambamba software were used to sort and remove duplicates to obtain the original bam file of the sample.

[0096] The original bam file of the sample was input into the software Msisensor2 for analysis to obtain the number of reads of different lengths of repeated base sequences in the target region, i.e., the sample data set.

[0097] Example 3 Prediction of microsatellite locus stability status

[0098] The sequencing depth of the target region was at least 400×, and subsequent calculations were performed when this depth was met.

[0099] For a specific microsatellite locus: chr2_47641559_CAGGT_27[A]_GGGTT, as shown in Table 2).

[0100] Table 2chr2_47641559_CAGGT_27[A]_GGGTT information

[0101] chromosome Location Repeating Unit Repeat times (γ) 3' flanking sequence 5' flanking sequence chr2 47641559 A 27 CAGGT GGGTT

[0102] The length distribution is shown in Table 3 and Figure 1 shown.

[0103] Table 3 Length distribution of chr2_47641559_CAGGT_27[A]_GGGTT

[0104]

[0105]

[0106] This embodiment uses five features of the peak number N, skewness Skew, kurtosis Kurt, standard deviation S, and standard deviation P of the repeated base sequence length in the target region to determine the MSI state.

[0107] For a specific repeated base sequence, the calculations are as follows.

[0108] Peak number calculation:

[0109] Count the sequencing depth of the target region, and count the number of peaks of the microsatellite locus length obtained according to the peak-finding algorithm. Specifically, Scipy is used to calculate the Peak Prominence calibration peak number and remove noise.

[0110] In this example, the peak number of chr2_47641559_CAGGT_27[A]_GGGTT is 1.

[0111] Using the known stable length γ of the microsatellite locus, the theoretical maximum length of the microsatellite locus is 2γ, that is, 54. Therefore, the number of length types of chr2_47641559_CAGGT_27[A]_GGGTT is n=54, i=[1, 54].

[0112] The skewness calculation formula is:

[0113]

[0114] The kurtosis calculation formula is:

[0115]

[0116] The formula for calculating standard deviation is:

[0117]

[0118] The standard deviation calculation formula is:

[0119]

[0120] Among them, x i is the number of reads when the length of the microsatellite locus is i; is the average number of reads of different lengths at microsatellite loci. i ′is the normalized value of the number of reads when the length of the microsatellite site is i, For x i ′ The mean of .

[0121] According to the above formula, the skewness, kurtosis, standard deviation and standard deviation of the length of chr2_47641559_CAGGT_27[A]_GGGTT are: 2.80, 9.87, 0.05 and 19.82 respectively.

[0122] Example 4 Establishing a logistic regression model to predict the stability of microsatellite loci

[0123] This embodiment uses 6 microsatellite loci with known stability data to establish a model to predict the stability of microsatellite loci with unknown stability data. The 6 microsatellite loci with known stability data are shown in Table 4.

[0124] Table 4 Six known microsatellite loci

[0125] Site number chromosome Location Repeating Unit Repeat times (γ) 3' flanking sequence 5' flanking sequence 1 chr11 102193508 A 26 CTGGT GCCAC 2 chr14 23652346 A 21 TTGCT GGCCA 3 chr4 55598211 T 25 TTTGA GAGAA 4 chr2 95849361 T 23 TCCTA GTGAG 5 chr2 47641559 A 27 CAGGT GGGTT 6 chr2 39564893 T 28 TCCAG GAGAC

[0126] In order to establish a microsatellite locus stability model, verify the MSI prediction results and evaluate its performance, the inventors performed MSI-PCR capillary electrophoresis detection on the samples, and the results were used as the gold standard to compare the consistency of the results between the two. The kit used for MSI-PCR capillary electrophoresis detection is the Paulownia microsatellite instability (MSI) detection kit (multiple fluorescence PCR-capillary electrophoresis method), and the status of each microsatellite locus in each sample and the overall MSI status of the sample are obtained according to MSI-PCR capillary electrophoresis detection.

[0127] Specifically, according to the results of MSI-PCR capillary electrophoresis, each microsatellite locus is divided into two categories: stable microsatellite locus and unstable microsatellite locus. If a microsatellite locus changes, that is, the length of the microsatellite locus changes significantly due to the insertion or deletion of a repeating unit, then the microsatellite locus is unstable; conversely, if a microsatellite locus does not change, that is, there is no change in the length of the microsatellite locus due to the insertion or deletion of a repeating unit, or even if there is an insertion or deletion of a repeating unit, the length change is not significant, then the marker microsatellite locus is stable.

[0128] For example, the results of MSI-PCR capillary electrophoresis at the BAT25 locus (chr4 55598211) are as follows: Figure 2 As shown, this point is homozygous. In the comparison between the tumor sample and the paired sample, it is not difficult to find that a new set of displacement peaks is added in the tumor sample (as shown by the dotted line in the figure). Therefore, this site is an unstable microsatellite site in the tumor sample, and a stable microsatellite site in the paired sample (blood).

[0129] Furthermore, according to the stability of microsatellite loci, the overall MSI status of the samples was divided into three types: MSI-H, MSI-L, and MSS, corresponding to microsatellite high instability, microsatellite low instability, and microsatellite stability.

[0130] MMS: All microsatellite loci are stable.

[0131] MSI-L: <30% of microsatellite loci are in an unstable state.

[0132] MSI-H: ≥30% of microsatellite loci are unstable.

[0133] In this example, MSI-PCR capillary electrophoresis data of 800 samples were obtained, including stability data of 6 microsatellite loci and MSI overall status data of 800 samples.

[0134] The MSI-PCR capillary electrophoresis data of the stability of the 6 microsatellite loci of the above 800 samples were processed, and the samples whose NGS results did not meet the quality control were removed to obtain a total of 3780 microsatellite loci stability data, which were randomly divided into training set and test set according to the ratio of 7:3 by stratified sampling. For the training set, based on the Msisensor2 result file obtained by Example 2, the lengths of the 6 microsatellite loci were calculated, and the peak number N, kurtosis Kurt, skewness Skew, standard deviation S, and standard deviation P of the length of each microsatellite locus were obtained by the method of Example 3 to generate training set data, and the unstable sample of the microsatellite locus was recorded as 1, and the stable sample of the microsatellite locus was recorded as 0 to form training set 1. The same method was used to obtain test set 1. The training set 1 data was trained based on the logistic regression model to obtain the logistic regression model of training set 1.

[0135] Based on the logistic regression model obtained from training set 1, the stability of microsatellite loci in test set 1 is predicted. According to the results of MSI-PCR capillary electrophoresis, the accuracy of the stability of microsatellite loci in the test set is evaluated. Then the model is modified, noise is removed, and model parameters and solution algorithms are modified. Finally, the model regularization parameter is specified as l2, the maximum number of iterations is 5000, and the classification type is binary. Because the number of unstable samples of microsatellite loci in the actual training set is far less than the number of stable samples (15:1), the penalty mode of the loss function is balance, and the L-BFGS algorithm is used to solve the problem to obtain the optimal logistic regression model model1. The performance evaluation is as follows: Figure 3 shown.

[0136] Based on the logistic regression model model1 obtained from training set 1, the stability of all 22 selected microsatellite loci was calculated to obtain a microsatellite locus data set, as shown in Table 5.

[0137] Table 5 22 microsatellite loci

[0138]

[0139]

[0140] Example 5 Establishing a random forest model to predict the overall MSI status of samples

[0141] The above 22 microsatellite loci data sets were randomly divided into training set and test set by stratified sampling in a ratio of 7:3 to obtain training set 2 and test set 2. The training set 2 data was trained based on the random forest model, and the penalty mode of the loss function was specified as balance to obtain the random forest model of training set 2.

[0142] Based on the random forest model obtained from training set 2, the overall MSI status of test set 2 is predicted, and the accuracy of the overall MSI status of the test samples is evaluated based on the MSI-PCR capillary electrophoresis results. Repeat the above steps until the optimal random forest model model2 is obtained. The performance evaluation results are shown in Figure 2. Figure 4 .

[0143] Example 6 Application of prediction model

[0144] 143 samples were obtained for NGS sequencing data analysis and calculation to obtain an external data set. The microsatellite site stability and overall MSI status of the external data set were predicted using logistic regression model model1 and random forest model model2, and the MSI overall status data obtained by MSI-PCR capillary electrophoresis in Example 4 were used for verification. The results are shown in Table 6.

[0145] Table 6 Validation results of 143 external samples

[0146]

[0147] It can be seen that the prediction model of the present invention has a sensitivity of 1 and a specificity of 0.92.

[0148] In actual clinical medication, MSI-L and MSS are generally classified into one category, namely MSI-L / MSS. The ROC curve of the model is obtained as follows Figure 5 As shown, the AUC is 0.99.

[0149] Example 7 System for determining the overall MSI status of a sample to be tested

[0150] This embodiment establishes a system for determining the overall MSI status of a sample to be tested based on the above method, such as Figure 6 As shown, including:

[0151] ① Sequencing data input module, used to input the capture sequencing data of the target region containing 22 microsatellite loci in the sample to be tested, and obtain the number of peaks, kurtosis, skewness, standard deviation and standard deviation of the length of the 22 microsatellite loci.

[0152] The quality control software Picard was used to perform quality control on the raw data obtained by capturing the sequencing data, filtering out sequencing adapters, low-quality bases, and sequencing error fragments, etc., and obtaining high-quality data (clean data) after filtering.

[0153] The clean data was compared and analyzed using the sequence alignment software bwa-MEM to obtain the specific genomic location information of the sequence (the reference genome was hg19); samtools and sambamba software were used to sort and remove duplicates to obtain the original bam file of the sample.

[0154] The original bam file of the sample was input into the software Msisensor2 for analysis to obtain the results of the length of the repeated base sequence (microsatellite site) in the target region.

[0155] For a certain microsatellite locus, the number of peaks of the microsatellite locus length is first counted according to the peak-finding algorithm, and then the skewness, kurtosis, standard deviation and standard deviation of the length of the microsatellite locus of the morphology are calculated using the following formulas:

[0156] The skewness calculation formula is:

[0157]

[0158] The kurtosis calculation formula is:

[0159]

[0160] The formula for calculating standard deviation is:

[0161]

[0162] The standard deviation calculation formula is:

[0163]

[0164] Among them, x i is the number of reads when the length of the microsatellite locus is i, i = [1, n]; is the mean number of reads of different lengths at the microsatellite locus; x i ′ is the normalized value of the number of reads when the length of the microsatellite site is i, For x i ′The mean value; n is the number of length types of the microsatellite locus, n = 2γ; γ is the standard value of the length of the microsatellite locus.

[0165] ② A microsatellite locus storage module, used to store the peak number, kurtosis, skewness, standard deviation and standard shift of the length of 6 microsatellite loci of the first population sample, as well as stability data;

[0166] ③ A marker microsatellite site stability prediction module is respectively connected to the sequencing data input module, the microsatellite site storage module and the marker microsatellite site data input module, and is used to construct a stability prediction model for 22 microsatellite sites using the peak number, kurtosis, skewness, standard deviation and standard deviation of the lengths of the 6 microsatellite sites of the first population sample and the stability data, and predict the stability of the 22 microsatellite sites based on the peak number, kurtosis, skewness, standard deviation and standard deviation of the lengths of the 22 microsatellite sites obtained from the sequencing data input module, and is used to output the stability data of the 22 microsatellite sites to the marker microsatellite site data input module.

[0167] The construction of a marker microsatellite locus stability prediction model using the peak number, kurtosis, skewness, standard deviation and standard shift of the known microsatellite locus length and stability data includes the following steps:

[0168] S11, randomly divide the peak number, kurtosis, skewness, standard deviation, standard shift and stability data of the known microsatellite loci length of the first population samples into two groups, one group is the first training set, and the other group is the first test set;

[0169] S12, using the first training set data, constructing a marker microsatellite locus stability prediction model based on a logistic regression algorithm;

[0170] S13, in the first test set, the obtained marker microsatellite locus stability prediction model is verified.

[0171] ④ A marker microsatellite locus data input module is used to receive stability data of 22 microsatellite loci of the sample to be tested, and the stability includes stable and unstable;

[0172] ⑤MSI overall status storage module, used to store the stability data of the marker microsatellite loci of the second population sample and the MSI overall status data, the MSI overall status includes MSI-H, MSI-L and MSS;

[0173] ⑥ An MSI overall status determination module is connected to the data input module and the MSI overall status storage module respectively, and is used to construct a prediction model using the stability data of the marker microsatellite loci of the second population sample, and determine the MSI overall status of the sample to be tested based on the stability data of the marker microsatellite loci of the sample to be tested obtained from the marker microsatellite loci stability prediction module.

[0174] The construction of a prediction model using the stability data of the marker microsatellite loci of the population sample includes the following steps:

[0175] S21, randomly dividing the stability data of the marker microsatellite loci of the second population samples into two groups, one group is a second training set, and the other group is a second test set, each group includes the stability data of the marker microsatellite loci of the MSI-H sample, the MSI-L sample, and the MSS sample;

[0176] S22, using the second training set data, constructing an MSI overall status prediction model based on a random forest algorithm;

[0177] S23, in the second test set, verifying the obtained MSI overall status prediction model.

[0178] All documents mentioned in the present invention are cited as references in this application, just as each document is cited as reference individually. In addition, it should be understood that after reading the above teachings of the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms also fall within the scope defined by the claims attached to this application.

Claims

1. A method for constructing a prediction model for the stability of a marker microsatellite locus, characterized in that: The marker microsatellite locus stability prediction model is constructed using the peak number, kurtosis, skewness, standard deviation and standard deviation of the known microsatellite locus lengths of the first population sample and the stability data, wherein: The known microsatellite loci include: The marker microsatellite loci include: The method comprises the following steps: S11, randomly divide the peak number, kurtosis, skewness, standard deviation, standard shift and stability data of the known microsatellite loci length of the first population samples into two groups, one group is the first training set, and the other group is the first test set; S12, using the first training set data, constructing a marker microsatellite locus stability prediction model based on a regression algorithm; S13, in the first test set, verifying the obtained marker microsatellite site stability prediction model.

2. The method according to claim 1, characterized in that For specific marker microsatellite loci: According to the peak-finding algorithm, the number of peaks of the length of the marker microsatellite locus is counted, and then the skewness, kurtosis, standard deviation and standard deviation of the length of the marker microsatellite locus are calculated using the following formulas: The skewness calculation formula is: The kurtosis calculation formula is: The formula for calculating standard deviation is: The standard deviation calculation formula is: Among them, x i is the number of reads when the length of the marker microsatellite site is i, i = [1, n]; is the mean number of reads of different lengths at the marker microsatellite locus; x i ′ is the normalized value of the number of reads when the length of the microsatellite site is i, For x i ′ The mean value; n is the number of length types of the marker microsatellite site, n = 2γ; γ is the standard value of the length of the marker microsatellite site.

Citation Information

Patent Citations

  • Method for simultaneously detecting microsatellite locus stability and genome change on basis of second generation sequencing

    CN106755501A

  • Microsatellite instability detection device, computer equipment and computer storage medium

    CN110689921A

  • Microsatellite instability prediction method and application thereof

    CN111304303A

  • Detection of microsatellite instability

    CN112639983A

  • Methods and systems for assessing microsatellite instability

    CN112955570A